我试图将IBM Watson的语音转文本功能实现到Discord.js机器人中，但是当我将PCM流从该机器人传递到STT识别器时，什么也没有发回，并且出现了超时错误。我试着在我的mp3文件中试了几次测试，结果很好，有人知道我在做什么错吗？

        // this creates a 16-bit signed PCM,stereo 48KHz stream
        const audioStream = receiver.createPCMStream(user)

        var params = {
            objectMode: true,contentType: 'audio/l16;rate=48000;channels=1',model: 'en-US_Broadbandmodel',maxAlternatives: 3
        };

        var recognizestream = speechToText.recognizeusingWebSocket(params);

        audioStream.pipe(recognizestream);

        // Listen for events.
        recognizestream.on('data',function (event) {
            console.log(event);
        });